Specifications Compared
| Spec | L40 | RTX A4000 |
|---|---|---|
| TDP | 300W | 140W |
| VRAM | 48 GB | 16-20 GB |
| CUDA Cores | 18,176 | 6,144 |
| FP8 (dense) | 362 TFLOPS | Not published |
| Memory Type | GDDR6 | GDDR6 |
| Architecture | Ada Lovelace | Ampere |
| FP16 (dense) | 181.05 TFLOPS | Not published |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 362 TOPS | Not published |
| Interconnect | PCIe 4.0 | PCIe 4.0 |
| Tensor Cores | 568 | 192 |
| FP32 Performance | 90.5 TFLOPS | 19.2 TFLOPS |
| Memory Bandwidth | 864 GB/s | 448 GB/s |
| FP8 (with sparsity) | 724 TFLOPS | Not published |
| FP16 (with sparsity) | 362.1 TFLOPS | 153.4 TFLOPS |
| INT8 (with sparsity) | 724 TOPS | Not published |
Performance Analysis
The L40 delivers 181.05 TFLOPS in dense FP16 while the RTX A4000 lists no dense FP16 figure. In sparse FP16 the L40 reaches 362.1 TFLOPS against 153.4 TFLOPS on the RTX A4000. The FP32 ratio of 90.5 TFLOPS to 19.2 TFLOPS shows the L40 provides 4.71 times the throughput of the RTX A4000. Memory bandwidth of 864 GB/s versus 448 GB/s allows the L40 to sustain larger batch sizes than the RTX A4000 in memory bound operations. These ratios indicate the L40 supports faster training iterations and higher inference throughput when dense FP16 or sparse FP16 figures are compared directly to their matching counterparts.
Current On-Demand Offers
Cheapest secure on-demand offer per provider that is reported in stock right now, per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site. Stock is rechecked every minute.
L40
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| ThunderCompute | USA | 1 | $0.79 | — | Deploy |
| RunPod | global | 1 | $0.82 | — | Deploy |
| Massed Compute | us-central-2 | 2 | $0.86 | $1.72 | Deploy |
| QuantaCloud | us-midwest-2 | 4 | $0.94 | $3.75 | Deploy |
| Hyperstack | CANADA-1 | 4 | $1.00 | $4.00 | Deploy |
5 providers in stock, 18 offers (cheapest per provider shown). All L40 offers, price history and alerts
RTX A4000
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Hyperstack | NORWAY-1 | 1 | $0.15 | — | Deploy |
| Paperspace | ny2 | 2 | $0.76 | $1.52 | Deploy |
2 providers in stock, 7 offers (cheapest per provider shown). All RTX A4000 offers, price history and alerts
Notify me when L40 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.79/GPU-hr.
QuantaCloud
Comparing providers? We broker across all of them.
Stop tab-switching between pricing pages. Tell us what you need, 16+ GPUs reserved or cluster capacity, and we return one quote at partner rates within 24 hours.
When to Choose the L40
The L40 suits workloads that require 48 GB of memory and 864 GB/s bandwidth. Models exceeding 20 GB benefit from the L40 capacity while its 90.5 TFLOPS FP32 and 181.05 TFLOPS dense FP16 accelerate compute heavy phases. Users select the L40 when scaling batch sizes beyond what 448 GB/s bandwidth permits on the RTX A4000.
When to Choose the RTX A4000
The RTX A4000 fits power constrained environments with its 140 W TDP. Tasks that fit within 16 to 20 GB memory and need only 19.2 TFLOPS FP32 operate efficiently on this card. Deployments limited to lower power draw choose the RTX A4000 over the 300 W L40.
Use Cases
The L40 provides 48 GB memory and 181.05 TFLOPS dense FP16 compared with 16 to 20 GB and no dense FP16 on the RTX A4000.
The L40 supplies 362.1 TFLOPS sparse FP16 and 864 GB/s bandwidth versus 153.4 TFLOPS sparse FP16 and 448 GB/s on the RTX A4000.
The L40 90.5 TFLOPS FP32 and 48 GB memory support larger fine tuning batches than the 19.2 TFLOPS FP32 and 16 to 20 GB on the RTX A4000.
Both cards handle diffusion workloads yet the L40 48 GB memory allows bigger batches while the RTX A4000 140 W TDP reduces power draw.
The L40 90.5 TFLOPS FP32 exceeds the RTX A4000 19.2 TFLOPS FP32 by a factor of 4.71.
Frequently Asked Questions
What is the FP32 performance difference?▾
The L40 reaches 90.5 TFLOPS FP32 and the RTX A4000 reaches 19.2 TFLOPS FP32.
Which GPU has higher memory bandwidth?▾
The L40 provides 864 GB/s bandwidth while the RTX A4000 provides 448 GB/s bandwidth.
How do the sparse FP16 figures compare?▾
The L40 achieves 362.1 TFLOPS with sparsity in FP16 and the RTX A4000 achieves 153.4 TFLOPS with sparsity in FP16.
What are the TDP ratings?▾
The L40 TDP is 300 W and the RTX A4000 TDP is 140 W.
Do both GPUs support the same interconnect?▾
Both the L40 and RTX A4000 use PCIe 4.0 interconnect.
Which is cheaper to rent, the L40 or the RTX A4000?▾
Cloud rental prices for both the L40 and RTX A4000 vary by provider, configuration, and availability. This page shows live pricing from 25+ providers updated every 60 seconds. Scroll to the Live Cloud Pricing section to compare current rates.
How much VRAM does the L40 have compared to the RTX A4000?▾
The L40 has 48 GB of GDDR6 memory. The RTX A4000 has 16 to 20 GB of GDDR6 memory.
Can I find L40 and RTX A4000 GPUs available to rent right now?▾
Yes. This page shows real-time availability across 25+ cloud GPU providers. The Live Cloud Pricing section displays only in-stock offers with current pricing.
What is the main difference between the L40 and the RTX A4000?▾
The L40 uses the Ada Lovelace architecture (2023) while the RTX A4000 uses Ampere (2021). The L40 has 48 GB of GDDR6 at 864 GB/s; the RTX A4000 has 16-20 GB of GDDR6 at 448 GB/s, so the L40 has 1.9x the memory bandwidth of the RTX A4000.
Rent these GPUs
Each GPU page lists every current on-demand offer by provider, per GPU-hour, updated every minute.
Related comparisons
How this page is made
- Specifications come from the NVIDIA, AMD and Intel datasheets for the L40 and the RTX A4000. Dense and sparse throughput are listed separately.
- Prices and availability are live: every offer shown is an in-stock, on-demand listing from a provider we track, rechecked every minute.
- The written comparison (overview, performance notes, when to choose each card, verdict, use cases and FAQ) was drafted with an AI model from the specification table above and passed an automated check that rejects any figure not in that table. It was last generated on . It contains no prices; those are always read live.
- Read how we collect the data, or report an error on this page.
Next steps
- Rent L40Every current offer by provider, daily price history and a price alert.
- Rent RTX A4000Every current offer by provider, daily price history and a price alert.
- GPU price indexHow on-demand prices for the major GPUs have moved, updated daily.
- All GPUsEvery GPU we track, with current lows and provider counts.